Multiobjective Deep Belief Networks Ensemble for Remaining Useful Life Estimation in Prognostics .pdf
2019-12-21 20:27:30 3.24MB Deep Belief Networks Ensemble
1
本书是Grégoire Montavon 2012年推出的第二版书,主要介绍神经网络的训练改进技巧、以及表示等等,本书高清无码扫描,附带完整标签,文字可编辑复制,并以保存为长期归档格式PDF/A!堪称完美!强烈推荐!
2019-12-21 20:24:10 9.66MB 机器学习 深度学习 Python 神经网络
1
Recurrent Neural Networks for Prediction offers a new insight into the learning algorithms, architectures and stability of recurrent neural networks and, consequently, will have instant appeal. It provides an extensive background for researchers, academics and postgraduates enabling them to apply such networks in new applications.
2019-12-21 20:22:21 5.61MB machine learning Neural Networks
1
computer networks 5th, Andrew Tanenbaum, David Wetherall, Prentice Hall, 2011, Solution, 答案解析
2019-12-21 20:18:41 170KB solution 答案 computer networks
1
MIT教材Data Networks全部的答案,不是一部分,1-6章都有。
2019-12-21 20:16:31 9.74MB Data Network Solutions 答案
1
可参看博客:https://blog.csdn.net/luolan9611/article/details/88578720 视觉问题回答(VQA)需要联合图像和自然语言问题,其中许多问题不能直接或清楚地从视觉内容中得到,而是需要从结构化人类知识推理并从视觉内容中得到证实。该论文提出了视觉知识记忆网络(VKMN)来解决这个问题,它将结构化的人类知识和深层视觉特征无缝融入端到端学习框架中的记忆网络中。与现有的利用外部知识支持VQA的方法相比,本文更多地强调了两种缺失的机制。首先是将视觉内容与知识事实相结合的机制。 VKMN通过将知识三元组(主体,关系,目标)和深层视觉特征联合嵌入到视觉知识特征中来处理这个问题。其次是处理从问题和答案对中扩展出多个知识事实的机制。VKMN使用键值对结构在记忆网络中存储联合嵌入,以便易于处理多个事实。实验表明,该方法在VQA v1.0和v2.0基准测试中取得了可喜的成果,同时在知识推理相关问题上优于最先进的方法。
2019-12-21 20:14:13 8.39MB VQA VKMN 视觉知识记忆
1
最经典的计算机网络著作。Andrew S. Tanenbaum的成名之作
2019-12-21 20:13:36 8.63MB 计算机网络
1
Long Short Term Memory Networks for Anomaly Detection in Time Series - LSTM在时序数据中的应用
2019-12-21 20:12:08 1.36MB ml last time series
1
介绍贝叶斯网络的概念和相关算法以及概率图模型,有例子介绍怎样使用概率图模型来做决策的。
2019-12-21 20:10:05 3.37MB 贝叶斯网络
1
A wireless communication network can be viewed as a collection of nodes, located in some domain, which can in turn be transmitters or receivers (depending on the network considered, nodes may be mobile users, base stations in a cellular network, access points of a WiFi mesh etc.). At a given time, several nodes transmit simultaneously, each toward its own receiver. Each transmitter–receiver pair requires its own wireless link. The signal received from the link transmitter may be jammed by the signals received from the other transmitters. Even in the simplest model where the signal power radiated from a point decays in an isotropic way with Euclidean distance, the geometry of the locations of the nodes plays a key role since it determines the signal to interference and noise ratio (SINR) at each receiver and hence the possibility of establishing simultaneously this collection of links at a given bit rate. The interference seen by a receiver is the sum of the signal powers received from all transmitters, except its own transmitter.
2019-12-21 20:10:03 2.03MB 通信
1